Enhanced Prediction of Lung Cancer Using Machine Learning

Lung cancer has emerged as major cause of cancer-related fatalities worldwide. Therefore, early lung cancer detection, prediction, and diagnosis have become essential because such diagnosis can accelerate and simplify clinical management. The healthcare sector has implemented several machine learning-based systems to improve the diagnosis and treatment of cancers based on their accurate results. Machine learning algorithms such as ETC (Extra Trees Classifier), NB (Naive Bayes), LR (Logistic Regression), EGB (Extreme Gradient Boosting), LGB (Light Gradient Boosting) Machine, KNN-Classifier, SVM-LinearKernel, DTC (Decision Tree Classifier), LDA (Linear Discriminant Analysis), GBC (Gradient Boosting Classifier), RC (Ridge Classifier), RFC (Random Forest Classifier), ABC (Ada-Boost Classifier), DC (Dummy classifier), and QDA (Quadratic-Discriminant-Analysis) are used in the healthcare industry to analyze and predict lung cancer progression. This research examined the current machine learning schemes reported their advantages and disadvantages. By reducing the need for researchers to review multiple publications, this paper will help them apply the relevant models more quickly and effectively.